Family
The person who missed the photo
Someone was working, someone was abroad, someone was holding the camera. A group shot with the missing person actually in it is the most common reason anyone looks for this at all.
Two photos · One instruction · A single frame in seconds
AI Picture Merger
Cutting one person out and pasting them beside another has never fooled anyone — the light gives it away in half a second. This rebuilds both photos into a single scene instead: one window, one shadow direction, one grain.
One light, not twoFaces that survive the tripNo cut-out edge
Before / after
Two rooms, two lightings, one photograph
Our own run on this site's engines. The two sources are deliberately mismatched — warm wall and hard side light on the left, cool grey and flat overhead on the right. Check her freckles and his beard survived before you judge the lighting. Every output is AI-generated.
Drag to compare before and after
AI image tool
What merging two pictures actually requires
Not a paste. The model has to read both photographs, decide what a single camera in a single room would have recorded, and rebuild the whole frame to that standard.
Image tool
Photo editors have offered a lasso and a layer stack for thirty years, and the results still read as fake to anyone glancing at them. The reason is that the hard part was never the cutting out — it is that two photographs carry two different physics. Different key direction, different colour temperature, different lens compression, different noise.
Paste one into the other and every one of those mismatches survives, which is why the eye catches it instantly even when the outline is perfect.
Our own run is the pair above, and the two sources were chosen to be awkward on purpose. She was shot against a warm-white wall with hard window light coming from her left; he was shot against cool grey under flat overhead light. Neither could be dropped into the other's frame. The output puts them in one living room under one window: her freckles and dark curls intact, his trimmed grey beard and pale blue shirt intact, a single shadow direction across both. Drag the divider and look at the two backgrounds first, then at whether either face changed.
Two honest limits. The room is invented — the model builds a plausible place rather than preserving either original background, so if the setting matters, describe it. And this is a rebuild, not a paste: at full zoom you are looking at a new photograph of both people, not their original pixels. If what you want is one picture repaired rather than two combined, old photo restoration is the other job.
Creative engine
How the merge runs
Upload both photos, say who stands where, compare the result against the sources at full size.
Two photos
Light, colour, grain
One frame
Similar framing merges best
Two waist-up shots combine far more easily than a full-length and a tight head-and-shoulders — the model has less scale to invent.
Name who is who
Describing each person by their clothing keeps the model from confusing which face belongs to which side of the frame.
How to use
Three steps to a frame that holds
Most of the quality is decided before the model runs, by which two photos you pick.
1
Pick two photos with similar framing
Two waist-up shots, or two head-and-shoulders. Combining a full-length with a tight crop forces the model to guess how big one person is relative to the other, and scale is the mistake nobody forgives.
2
Say who stands where, by their clothes
"The woman in the mustard cardigan on the left, the man in the navy jacket on the right." Naming them by wardrobe rather than by position alone is what stops the two faces getting swapped between sides.
3
Check the faces before you check the lighting
The lighting is almost always convincing — that is the part the model is good at. Identity is where a merge quietly fails. Put the result beside both sources at full size and confirm you would still recognise each person.
Who it's for
Why people put two photos together
Four briefs, and most of them are about someone who was not in the room.
Memory
The relative who is gone
A grandparent and a grandchild who never overlapped. It is a picture that could not have been taken, and for a lot of families that is exactly the point of taking it.
Commerce
The product and the place
A packshot on white and an empty interior become one photograph of the thing in a room. Same discipline as [cleaning up a product shot](/image/ai-product-photo-editor), one step further on.
Personal
The long-distance pair
Two selfies from two cities, one frame that looks like an afternoon together. The lighting match is what decides whether it reads as sweet or as a bad collage.
Answers
Merging FAQ
What people check before trusting a combined photograph.
Two. That is what the generator on this page takes, and it is also the case that behaves most predictably — the more people the model has to place, scale and relight against each other, the more likely one of them drifts. Merge two, then merge the result with a third if you need more.
That is the thing to check every time, and it is why the demo above asks you to look at her freckles and his beard rather than at the lighting. A merge that returns two convincing strangers has failed at the only job that mattered. If a face drifts, name that person's features explicitly in the prompt and rerun.
Because neither original background can hold both people — one was shot against a warm wall, the other against cool grey. Rather than pick a winner and relight the other person badly, the model builds one room that suits them both. Describe the setting you want if it matters.
Yes, and it is one of the most common reasons people come here. The catch is film grain and colour: a 1970s print and a phone photo carry very different textures, and unifying them means one of the two moves further from how it originally looked. Usually the older photo is the one that changes most.
No. A face swap puts one person's face onto another person's body in a single photo. This keeps both people whole and builds a frame that contains them both — different job, different failure modes. If you want two people in one shot rather than one identity on another, this is the page.
Over HTTPS for the merge, into your own history, and nowhere else. They are never used to advertise, and deleting them removes them. Every output is AI-generated.
Kavel pricing — pay only for what you generate
One credit pool covers Nano Banana images and Seedance and Veo video. The cost shows before every run, and failed jobs are not charged. Use a subscription for ongoing work, or a one-time pack when you just need to top up.
50% OFFLimited-time half price — lock it in now
No sign-upIncl. taxStart generating
Free
Start generating before you pay anything, and keep earning credits every day you come back. No card, no account needed.
$0
What's included
- Free credits before you even sign up — no account needed
- A sign-up bonus the moment you create one
- Daily check-in credits that climb through the week
- Photo editing on Nano Banana 2 Lite
- Every model on this page stays visible — upgrade to unlock
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
Start hereIncl. tax
Starter
A monthly balance that keeps a steady run of clips and images going — on every model Kavel carries.
$59.80
The whole shelf is open from day one.$29.90 / month
Quantity1x · $29.90
Total: 3,150 credits
What's included
- Videos from $0.15 · images from $0.02
- 3,150 credits per month
- Up to 210 videos or 1,570 images a month
- Clean downloads, no watermark
- Works with Nano Banana images and Seedance and Veo video
- Cost preview before you generate
- Generation history
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
PopularPopular
Creator
For regularly making Kavel drafts, final clips, and the image assets that go with them.
$119.80
The best pick if you create on a regular basis.$59.90 / month
Quantity1x · $59.90
Total: 7,200 credits
What's included
- Videos from $0.13 · images from $0.017
- 7,200 credits per month
- Up to 480 videos or 3,600 images a month
- Clean downloads, no watermark
- Access to Seedance 2.0, Fast, and Mini
- Nano Banana 2 generation and editing
- Priority credit top-ups
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
ScaleIncl. tax
Studio
For more output, high-resolution testing, and larger batches.
$199.80
Ideal when several campaigns share one pool.$99.90 / month
Quantity1x · $99.90
Total: 13,200 credits
What's included
- Videos from $0.12 · images from $0.016
- 13,200 credits per month
- Up to 880 videos or 6,600 images a month
- Clean downloads, no watermark
- Built for high-volume Kavel generation
- Plenty of room for 4K Kavel runs
- Available across the supported models
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
Credit packs
One-time top-ups — buy extra credits any time you run low.
Credit Pack 1500
Pay once, generate whenever. Credits land instantly and never expire.
$39.80
$19.90
Quantity1x · $19.90
Total: 1,500 credits
What's included
- Videos from $0.20 · images from $0.027
- 1,500 credits
- Up to 100 videos or 750 images
- Clean downloads, no watermark
- No ongoing subscription
- Available across the supported models
- Credits never expire
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
Flexible
Credit Pack 3600
Pay once for a run of final video renders. Credits land instantly and never expire.
$79.80
$39.90
Quantity1x · $39.90
Total: 3,600 credits
What's included
- Videos from $0.17 · images from $0.023
- 3,600 credits
- Up to 240 videos or 1,800 images
- Clean downloads, no watermark
- No ongoing subscription
- Available across the supported models
- Use for both video and image generation
- Credits never expire
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
Batch
Credit Pack 9000
A production-scale top-up for large prompt batches.
$159.80
$79.90
Quantity1x · $79.90
Total: 9,000 credits
What's included
- Videos from $0.14 · images from $0.018
- 9,000 credits
- Up to 600 videos or 4,500 images
- Clean downloads, no watermark
- No ongoing subscription
- Handy for Seedance 2.0 final renders
- Credits never expire
VISAAMEXPayGooglePaylink
Secure checkout by Stripe. Card details never touch our servers.
Not sure which to choose? Contact us
Charges appear as “KAVEL AI” on your card statement. You can cancel any time from Settings → Billing; cancellation takes effect at the end of the period you already paid for. Operator details, the full model list, and the refund window are on the about page.
Powered by
One credit balance for every Kavel image and video model
Use one balance across every supported image and video model — all of them listed below — and check the credit cost before each request.
Video models
Seedance 2.5 — up to 30 seconds in one generationSeedance 2.0, Fast and MiniSeedance 1.5 ProVeo 3.1 (Lite / Fast)Kling 3.0LTX 2.5MiniMax H3Text-to-video, image-to-video and video-input workflowsCost preview before you generate
Image models
Nano Banana 2Nano Banana ProNano Banana 2 LiteGPT Image 2Seedream 5.0 LiteQwen Image 3Grok Imagine Image 2.0Text-to-image and image-editing workflowsOne shared credit balance
Model credit guide
What each model costs in credits
You're only charged for successful generations. The exact estimate in the generator varies by model, length, resolution, audio, and number of images.
| Type | Model | Credit cost |
|---|---|---|
| Video | Seedance 2.5 | The long-take tier, priced per second: 5s 480p ≈ 211 credits, 5s 720p ≈ 473. A full 30s take runs ≈ 1,260 at 480p and ≈ 2,835 at 720p. Supplying a reference clip lowers the per-second rate. |
| Video | Seedance 2.0 | 5s 720p image-to-video ≈ 188 credits; text-to-video ≈ 308 credits. Scales with resolution and length. |
| Video | Seedance 2 Fast | Faster and lower cost. 5s 720p text-to-video ≈ 248 credits. |
| Video | Seedance 2 Mini | The cheapest Seedance tier. 5s 720p ≈ 154 credits, 5s 480p ≈ 72 credits. |
| Video | Seedance 1.5 Pro | Audio doubles the rate. 5s 720p ≈ 27 credits silent, ≈ 53 with audio; 1080p ≈ 57 and ≈ 113. |
| Video | Veo 3.1 | Billed per video, not per second (Lite tier). About 45 credits at 720p and 53 at 1080p. |
| Video | Kling 3.0 | Audio raises the rate. 5s 720p ≈ 105 credits silent, ≈ 150 with audio; 1080p ≈ 135 and ≈ 203. |
| Video | MiniMax H3 | Fixed 2K, no resolution ladder. Priced per second — a 5s clip ≈ 158 credits. |
| Image | Nano Banana 2 | Generate or edit from text and images. 20 credits per 1K image, 30 at 2K, 45 at 4K. |
| Image | Nano Banana Pro | Consistent run times across generations. 30 credits per 1K or 2K image, 50 at 4K. |
| Image | Nano Banana 2 Lite | Faster, simpler variant, and the everyday editing price: a flat 8 credits per image at every resolution. |
| Image | GPT Image 2 | The lowest-cost premium image model here. 10 credits per 1K image, 15 at 2K, 30 at 4K. |
| Image | Seedream 5.0 Lite | Flat pricing — 20 credits per image whether you generate or edit. |
More tools
Other ways to fix what the camera got wrong
Same rebuild-the-whole-frame discipline, different starting problem.
Put them both in one frame
Upload two photos, check both faces survived at full size, and keep the run where the shadows agree — or [repair the older print first](/image/old-photo-restoration).